IF YOU WOULD LIKE TO GET AN ACCOUNT, please write an email to s dot adaszewski at gmail dot com. User accounts are meant only to report issues and/or generate pull requests. This is a purpose-specific Git hosting for ADARED projects. Thank you for your understanding!
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
Stanislaw Adaszewski 2eff854467 Start working on FastLoop. 3 years ago
..
unused Remove loss as no longer necessary. 3 years ago
__init__.py Work on icosagon.trainprep. 3 years ago
batch.py Introduce FlatPredictions, flatten_predictions(), BatchIndices, gather_batch_indices(). 3 years ago
bulkdec.py Fix a typo. 3 years ago
compile.py Performance tests. 3 years ago
convlayer.py Add BatchedData support to DecodeLayer. 3 years ago
convolve.py Remove an extra newline. 3 years ago
data.py Clean up _equal(). 3 years ago
databatch.py Add BatchedData support to DecodeLayer. 3 years ago
declayer.py Add BatchedData support to DecodeLayer. 3 years ago
decode.py Use torch.nn.Parameter(List) in decode. 3 years ago
dropout.py Remove unnecessary .detach() call in dropout_dense(). 3 years ago
fastconv.py Reimplement FastConvLayer. 3 years ago
fastloop.py Start working on FastLoop. 3 years ago
fastmodel.py Add test_fast_model_01(). 3 years ago
input.py Fix for non-leaf .grad warning. 3 years ago
model.py Add TrainLoop. 3 years ago
normalize.py Fixes for bool sparse tensors. 3 years ago
sampling.py Fixes for the GPU. 3 years ago
trainloop.py Add some debug output for profiling, the bottleneck is in DecodeLayer but also comes generally from computing always all nodes. 3 years ago
trainprep.py Fixes for the GPU. 3 years ago
weights.py Bring more elements to icosagon. 3 years ago